Evolving neural arrays: a new mechanism for learning complex action sequences

Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus incr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Corbalán, Leonardo César, Lanzarini, Laura Cristina
Formato: Articulo
Lenguaje:Inglés
Publicado: 2017
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/103776
http://www.clei.org/cleiej/index.php/cleiej/article/view/348
Aporte de:
id I19-R120-10915-103776
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
spellingShingle Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
Corbalán, Leonardo César
Lanzarini, Laura Cristina
Evolving neural arrays: a new mechanism for learning complex action sequences
topic_facet Ciencias Informáticas
Evolving neural nets
Learning
Complex actions sequence learning
Incremental evolution
Genetic algorithms
description Incremental evolution has proved to be an extremely useful mechanism in complex actions sequence learning. Its performance is based on the decomposition of the original problem into increasingly complex stages whose learning is carried out sequentially, starting from the simplest stage and thus increasing its generality and difficulty. The present work proposes neural array applications as a novel mechanism for complex actions sequence learning. Each array is composed by several neural nets obtained by means of an evolving process allowing them to acquire various degrees of specialization. Neural nets constituting the same array are organized so that, in each assessment, there is only one in charge of its response. The proposed strategy is applied to problems presented by obstacle evasion and target reaching as a means to show the capability of this proposal to solve complex problems. The measurements carried out show the superiority of evolving neural arrays over traditional neuroevolving methods that handle neural network populations – SANE is being particularly used as a comparative reference due to its high performance. Neural array capability to recover from previous defective evolving stages has been tested, evincing highly plausible final successful outcomes – even in those adverse cases. Finally, conclusions are presented as well as some future lines of work.
format Articulo
Articulo
author Corbalán, Leonardo César
Lanzarini, Laura Cristina
author_facet Corbalán, Leonardo César
Lanzarini, Laura Cristina
author_sort Corbalán, Leonardo César
title Evolving neural arrays: a new mechanism for learning complex action sequences
title_short Evolving neural arrays: a new mechanism for learning complex action sequences
title_full Evolving neural arrays: a new mechanism for learning complex action sequences
title_fullStr Evolving neural arrays: a new mechanism for learning complex action sequences
title_full_unstemmed Evolving neural arrays: a new mechanism for learning complex action sequences
title_sort evolving neural arrays: a new mechanism for learning complex action sequences
publishDate 2017
url http://sedici.unlp.edu.ar/handle/10915/103776
http://www.clei.org/cleiej/index.php/cleiej/article/view/348
work_keys_str_mv AT corbalanleonardocesar evolvingneuralarraysanewmechanismforlearningcomplexactionsequences
AT lanzarinilauracristina evolvingneuralarraysanewmechanismforlearningcomplexactionsequences
bdutipo_str Repositorios
_version_ 1764820441150521344